Hydroponic crop production in smart greenhouses requires accurate nutrient monitoring and reliable control, especially in recirculating systems. This review critically examines sensing principles, data acquisition, control strategies, actuation, feedback, and system integration. Electrical conductivity (EC) and pH are widely used for dosing, but EC cannot quantify individual nutrient concentrations. Emerging technologies include ion-selective electrodes, solid contact and field effect sensors, optical spectroscopy, multi-sensor arrays, and Internet of Things platforms. Their deployment remains constrained by interference, drift, fouling, reference instability, calibration demands, and matrix effects. Control approaches range from threshold-based dosing and EC/pH feedback to proportional–integral–derivative, rule-based, ion-specific, and model-based strategies. Published ion-specific replenishment and hybrid EC–ion studies demonstrate feasibility under tested conditions. However, differences in nutrient formulations, study duration, and error definitions limit conclusions about commercial control accuracy. This review proposes an integrated framework linking sensing, decision making, actuation, and verification, with performance assessed at analytical, temporal, operational, and system/control levels. Future research should prioritize reliable multi-ion sensing, automated data quality checks, delivered dose verification, safe operation during faults, and communication between components. Validation should include complete crop cycles, maintenance, fault recovery, and independent sites. These requirements support evaluation of nutrient use efficiency, operational reliability, and scalability across crops and hydroponic systems under realistic production conditions.

Understanding greenhouse microclimatic variability is essential for precise environmental monitoring and control. This study evaluated temperature, relative humidity, CO₂ concentration, and light intensity variability in Korean greenhouses during summer and winter, and developed artificial neural network (ANN) models to predict indoor temperature and relative humidity at different layers. A glass greenhouse and an arched-frame double-layer plastic greenhouse were monitored during summer and winter, respectively. A wireless sensor network was deployed at multiple spatial positions and vertical layers, and layer-specific artificial neural network (ANN) models were developed to predict indoor temperature and relative humidity at the top, middle, and bottom layers. The measured results revealed clear temperature and humidity stratification, with the top layer generally showing a higher temperature and lower humidity than the middle and bottom layers. In summer, temperatures reached 36.4 °C, while relative humidity ranged from 55% to 92%, while in winter, temperature varied from 3.4 °C to 35.0 °C and relative humidity ranged from 73% to 91%. Spatial contour mapping showed clear microclimatic gradients, and ANOVA with Tukey’s HSD tests confirmed significant differences among sensor locations (p < 0.05). The ANN models predicted indoor temperature with high accuracy, with R² values generally above 0.95, while humidity prediction showed larger errors.

Warm-season greenhouse crops such as tomato (Solanum lycopersicum L.) and paprika (Capsicum annuum L.) require nutrient supply strategies that respond dynamically to temperature, solar radiation, vapor pressure deficit (VPD), root zone water status, and electrical conductivity (EC). This systematic review assessed four operational strategies: (1) solar radiation-proportional irrigation; (2) radiation-rate-based volume and EC adjustment; (3) supply–drainage and substrate-feedback control; and (4) temperature, humidity, and VPD-based supervisory correction. Scopus, Web of Science, IEEE Xplore, ScienceDirect, and MDPI were searched on 15 August 2026 for studies published from 2010 onward, yielding 4088 records (2326 after removal of duplicates). Studies were eligible if they addressed a controlled-environment production system, a warm-season crop, a nutrient-management component, and the use of sensing, automated control, models or decision-support systems, or IoT/AI tools. After title/abstract screening and full-text assessment, 90 studies were included: 29 studies from the database search and 61 studies identified by manual searching of publisher platforms, the three other references were from textbooks. Radiation-based approaches provide practical feedforward estimation but incompletely represent humidity and root zone dynamics. Supply–drainage feedback offers stronger closed-loop information, while temperature and VPD-based correction improves responsiveness to atmospheric demand. Tomato requires careful calcium and potassium management during reproductive stages, whereas paprika demands stable substrate moisture, EC, and drainage. A conceptual hierarchical framework is proposed in which solar radiation establishes the baseline nutrient-solution supply, radiation-rate information provides short-term adjustment, root-zone and drainage measurements provide feedback correction, and temperature or VPD serves as a supervisory layer. Ion-specific sensing, mechanistic models, and AI/ML approaches can further support nutrient-specific and predictive management. Few included studies evaluated these strategies under explicitly imposed high-temperature conditions; therefore crop, cultivar, and growth-stage-specific validation under commercial high-temperature greenhouse conditions is required before operational thresholds can be generalized.

Reliable environmental sensing is essential for stable monitoring and control in vertical farms; however, high data-acquisition completeness does not ensure that measurements are valid, temporally consistent, or operationally meaningful. This study proposed an interpretable two-layer framework that distinguished direct signal-quality errors from in-range temporal and operating-context abnormalities in a Wi-Fi-based small-scale vertical farm. Nine sensor nodes were installed across nine cultivation beds under empty-bed and continuous LED-on conditions. Air temperature, relative humidity, CO₂ concentration, and light intensity were measured at 30 s intervals for 10 days and transmitted through MQTT, Node-RED, and InfluxDB on a Raspberry Pi local server. Layer 1 screened timestamp discontinuities, invalid or null packets, and physically invalid measurements. Layer 2 evaluated only valid records using moving-window variability, rate of change, peer-node residuals, and LED-on context consistency, and a study-specific F-code taxonomy converted detected abnormalities into interpretable operating-status labels. Detection thresholds were determined from a separate two-day period immediately preceding the 10-day evaluation and were not adjusted using the evaluation records. Of 259,200 expected records, 258,910 were received (99.888% completeness). Layer 1 identified 290 missing timestamp positions, 25 invalid packets, and 40 out-of-range records. The framework achieved 99.68% accuracy, 98.49% precision, 98.89% recall, 98.69% binary F1 score, and 84.69% macro-averaged F-code F1 score. Combining signal validation with temporal and context analysis detected abnormalities that static range validation could not identify.

Accurate, non-destructive estimation of potato volume can support conveyor-based yield monitoring, but individual sensing modalities provide incomplete geometric information. This study developed and evaluated a low-cost sensing approach combining top-view RGB imaging and ultrasonic height measurement under controlled potato-harvester conveyor conditions. One hundred potatoes were evaluated repeatedly under 20 combinations of five conveyor speeds (0.10–0.50 ms⁻¹ and four inclination angles (15–30°). Two RGB cameras provided projected-area measurements across the conveyor width, while an eight-sensor ultrasonic array provided complementary potato-height measurements. Four linear volume-estimation formulations were compared: height only, projected area only, area and height as separate predictors (A+H), and an area–height fusion feature (A×H). The combined models substantially outperformed the single-sensor approaches. The (A+H) model achieved a mean (R²) of 0.88, RMSE of 3.27 cm³, and MAE of 2.54 cm³, while the (A×H) fusion model achieved a mean (R²) of 0.88, RMSE of 3.33 cm³, and MAE of 2.60 cm³. Mixed-effects analysis showed that model type significantly affected estimation error (p < 0.001), confirming the benefit of combining RGB-derived area and ultrasonic height. Conveyor speed had the dominant effect on accuracy (p < 0.001), whereas inclination angle produced a statistically significant but comparatively small effect, and the speed × angle interaction was non-significant. The highest accuracy was obtained at 0.10 ms⁻¹, while performance declined with increasing speed, consistent with reduced RGB and ultrasonic sampling opportunities. These results demonstrate the feasibility of RGB–ultrasonic fusion for potato volume estimation under controlled dynamic conveyor conditions; field-scale robustness remains to be validated under commercial harvesting environments.